Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/36844
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings
Peer Review Status: Refereed
Author(s): Swingler, Kevin
Rumble, Teri
Goutcher, Ross
Hibbard, Paul
Donoghue, Mark
Harvey, Dan
Contact Email: kevin.swingler@stir.ac.uk
Title: Combined Depth and Semantic Segmentation from Synthetic Data and a W-Net Architecture
Citation: Swingler K, Rumble T, Goutcher R, Hibbard P, Donoghue M & Harvey D (2024) Combined Depth and Semantic Segmentation from Synthetic Data and a W-Net Architecture. In: volume 1. 16th International Conference on Neural Computation Theory and Applications, Porto, Portugal, 20.11.2024-22.11.2024. SCITEPRESS - Science and Technology Publications, pp. 413-422. https://doi.org/10.5220/0012877500003837
Issue Date: 23-Nov-2024
Date Deposited: 25-Nov-2024
Conference Name: 16th International Conference on Neural Computation Theory and Applications
Conference Dates: 2024-11-20 - 2024-11-22
Conference Location: Porto, Portugal
Abstract: Monocular pixel level depth estimation requires an algorithm to label every pixel in an image with its estimated distance from the camera. The task is more challenging than binocular depth estimation, where two cameras fixed a small distance apart are used. Algorithms that combine depth estimation with pixel level semantic segmentation show improved performance but present the practical challenge of requiring a dataset that is annotated at pixel level with both class labels and depth values. This paper presents a new convolutional neural network architecture capable of simultaneous monocular depth estimation and semantic segmentation and shows how synthetic data generated using computer games technology can be used to train such models. The algorithm performs at over 98% accuracy on the segmentation task and 88% on the depth estimation task.
Status: VoR - Version of Record
Rights: Paper published under CC license (CC BY-NC-ND 4.0) in Proceedings of the 16th International Joint Conference on Computational Intelligence (IJCCI 2024), pages 413-422 ISBN: 978-989-758-721-4; ISSN: 2184-3236 Proceedings Copyright © 2024 by SCITEPRESS – Science and Technology Publications, Lda.
Licence URL(s): http://creativecommons.org/licenses/by-nc-nd/4.0/

Files in This Item:
File Description SizeFormat 
128775.pdfFulltext - Published Version731.67 kBAdobe PDFView/Open



This item is protected by original copyright



A file in this item is licensed under a Creative Commons License Creative Commons

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.